Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1732 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.7169. Min Act: -0.0000

Data Index: 383405 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.9415. Min Act: -0.0000

Data Index: 778473 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.7227. Min Act: -0.0000

Data Index: 1001842 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.8530. Min Act: -0.0000

Data Index: 1151134 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.8307. Min Act: -0.0001

Data Index: 710432 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.6704. Min Act: -0.0000

Data Index: 1183955 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.7675. Min Act: -0.0000

Data Index: 1189760 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.4237. Min Act: -0.0001

Data Index: 406998 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.4019. Min Act: -0.0000

Data Index: 215066 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.4482. Min Act: -0.0000

Data Index: 767601 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.4344. Min Act: -0.0000

Data Index: 979261 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.4089. Min Act: -0.0000

Data Index: 18450 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.1503. Min Act: -0.0001

Data Index: 806624 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 1.9415. Min Range: -1.9415

Max Act: 0.9406. Min Act: -0.0001

Data Index: 831400 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.3061. Min Act: -0.0000

Data Index: 203103 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.2230. Min Act: -0.0001

Data Index: 968644 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.1378. Min Act: -0.0000

Data Index: 809652 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.2468. Min Act: -0.0001

Data Index: 975054 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.1100. Min Act: -0.0000

Data Index: 466724 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.1271. Min Act: -0.0001

Data Index: 426378 (C4 (Web Text))

Max Activating Token Index: 268